Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to separations or exceptions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Thomas
    -0.50
     Ver
    -0.49
    Ve
    -0.48
    Lu
    -0.47
    Thomas
    -0.46
     Lu
    -0.46
    Coc
    -0.46
     Na
    -0.46
     ver
    -0.46
    Ver
    -0.45
    POSITIVE LOGITS
     fhort
    1.02
     madonna
    1.01
     ftre
    1.01
     paillettes
    1.00
     poff
    0.99
     bordeaux
    0.96
     ecru
    0.96
     chèvre
    0.96
     outlander
    0.96
     difp
    0.95
    Act Density 0.085%

    No Known Activations